release: 0.2.17

.github/workflows/ci.yml

@@ -0,0 +1,96 @@
+name: CI
+on:
+  push:
+    branches-ignore:
+      - 'generated'
+      - 'codegen/**'
+      - 'integrated/**'
+      - 'stl-preview-head/**'
+      - 'stl-preview-base/**'
+  pull_request:
+    branches-ignore:
+      - 'stl-preview-head/**'
+      - 'stl-preview-base/**'
+
+jobs:
+  lint:
+    timeout-minutes: 10
+    name: lint
+    runs-on: ${{ github.repository == 'stainless-sdks/llama-stack-client-python' && 'depot-ubuntu-24.04' || 'ubuntu-latest' }}
+    if: github.event_name == 'push' || github.event.pull_request.head.repo.fork
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Rye
+        run: |
+          curl -sSf https://rye.astral.sh/get | bash
+          echo "$HOME/.rye/shims" >> $GITHUB_PATH
+        env:
+          RYE_VERSION: '0.44.0'
+          RYE_INSTALL_OPTION: '--yes'
+
+      - name: Install dependencies
+        run: rye sync --all-features
+
+      - name: Run lints
+        run: ./scripts/lint
+
+  build:
+    if: github.repository == 'stainless-sdks/llama-stack-client-python' && (github.event_name == 'push' || github.event.pull_request.head.repo.fork)
+    timeout-minutes: 10
+    name: build
+    permissions:
+      contents: read
+      id-token: write
+    runs-on: depot-ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Rye
+        run: |
+          curl -sSf https://rye.astral.sh/get | bash
+          echo "$HOME/.rye/shims" >> $GITHUB_PATH
+        env:
+          RYE_VERSION: '0.44.0'
+          RYE_INSTALL_OPTION: '--yes'
+
+      - name: Install dependencies
+        run: rye sync --all-features
+
+      - name: Run build
+        run: rye build
+
+      - name: Get GitHub OIDC Token
+        id: github-oidc
+        uses: actions/github-script@v6
+        with:
+          script: core.setOutput('github_token', await core.getIDToken());
+
+      - name: Upload tarball
+        env:
+          URL: https://pkg.stainless.com/s
+          AUTH: ${{ steps.github-oidc.outputs.github_token }}
+          SHA: ${{ github.sha }}
+        run: ./scripts/utils/upload-artifact.sh
+
+  test:
+    timeout-minutes: 10
+    name: test
+    runs-on: ${{ github.repository == 'stainless-sdks/llama-stack-client-python' && 'depot-ubuntu-24.04' || 'ubuntu-latest' }}
+    if: github.event_name == 'push' || github.event.pull_request.head.repo.fork
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Rye
+        run: |
+          curl -sSf https://rye.astral.sh/get | bash
+          echo "$HOME/.rye/shims" >> $GITHUB_PATH
+        env:
+          RYE_VERSION: '0.44.0'
+          RYE_INSTALL_OPTION: '--yes'
+
+      - name: Bootstrap
+        run: ./scripts/bootstrap
+
+      - name: Run tests
+        run: ./scripts/test

.gitignore

@@ -1,5 +1,4 @@
 .prism.log
-.vscode
 _dev
 
 __pycache__

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.1.0-alpha.4"
+  ".": "0.2.17"
 }

.stats.yml

@@ -1,4 +1,4 @@
-configured_endpoints: 105
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-df7a19394e9124c18ec4e888e2856d22b5ebfd6fe6fe6e929ff6cfadb2ae7e2a.yml
-openapi_spec_hash: 9428682672fdd7e2afee7af9ef849dc9
-config_hash: e1d37a77a6e8ca86fb6bccb4b0f172c9
+configured_endpoints: 106
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-f59f1c7d33001d60b5190f68aa49eacec90f05dbe694620b8916152c3922051d.yml
+openapi_spec_hash: 804edd2e834493906dc430145402be3b
+config_hash: de16e52db65de71ac35adcdb665a74f5

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "python.analysis.importFormat": "relative",
+}

README.md

@@ -1,5 +1,6 @@
 # Llama Stack Client Python API library
 
+
 [![PyPI version](https://img.shields.io/pypi/v/llama_stack_client.svg)](https://pypi.org/project/llama_stack_client/) [![PyPI - Downloads](https://img.shields.io/pypi/dm/llama-stack-client)](https://pypi.org/project/llama-stack-client/)
 [![Discord](https://img.shields.io/discord/1257833999603335178)](https://discord.gg/llama-stack)
 

api.md

@@ -453,6 +453,18 @@ Methods:
 
 - <code title="get /v1/inspect/routes">client.routes.<a href="./src/llama_stack_client/resources/routes.py">list</a>() -> <a href="./src/llama_stack_client/types/route_list_response.py">RouteListResponse</a></code>
 
+# Moderations
+
+Types:
+
+```python
+from llama_stack_client.types import CreateResponse
+```
+
+Methods:
+
+- <code title="post /v1/openai/v1/moderations">client.moderations.<a href="./src/llama_stack_client/resources/moderations.py">create</a>(\*\*<a href="src/llama_stack_client/types/moderation_create_params.py">params</a>) -> <a href="./src/llama_stack_client/types/create_response.py">CreateResponse</a></code>
+
 # Safety
 
 Types:

pyproject.toml

@@ -3,7 +3,7 @@ name = "llama_stack_client"
 version = "0.2.17"
 description = "The official Python library for the llama-stack-client API"
 dynamic = ["readme"]
-license = "Apache-2.0"
+license = "MIT"
 authors = [{ name = "Meta Llama", email = "[email protected]" }]
 dependencies = [
     "httpx>=0.23.0, <1",
@@ -27,13 +27,14 @@ classifiers = [
   "Typing :: Typed",
   "Intended Audience :: Developers",
   "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
   "Operating System :: OS Independent",
   "Operating System :: POSIX",
   "Operating System :: MacOS",
   "Operating System :: POSIX :: Linux",
   "Operating System :: Microsoft :: Windows",
   "Topic :: Software Development :: Libraries :: Python Modules",
-  "License :: OSI Approved :: Apache Software License"
+  "License :: OSI Approved :: MIT License"
 ]
 
 [dependency-groups]
@@ -52,8 +53,6 @@ dev = [
 Homepage = "https://github.com/llamastack/llama-stack-client-python"
 Repository = "https://github.com/llamastack/llama-stack-client-python"
 
-
-
 [build-system]
 requires = ["hatchling==1.26.3", "hatch-fancy-pypi-readme"]
 build-backend = "hatchling.build"

requirements-dev.lock

@@ -48,15 +48,15 @@ filelock==3.12.4
 frozenlist==1.6.2
     # via aiohttp
     # via aiosignal
-h11==0.14.0
+h11==0.16.0
     # via httpcore
-httpcore==1.0.2
+httpcore==1.0.9
     # via httpx
 httpx==0.28.1
     # via httpx-aiohttp
     # via llama-stack-client
     # via respx
-httpx-aiohttp==0.1.6
+httpx-aiohttp==0.1.8
     # via llama-stack-client
 idna==3.4
     # via anyio

requirements.lock

@@ -36,14 +36,14 @@ exceptiongroup==1.2.2
 frozenlist==1.6.2
     # via aiohttp
     # via aiosignal
-h11==0.14.0
+h11==0.16.0
     # via httpcore
-httpcore==1.0.2
+httpcore==1.0.9
     # via httpx
 httpx==0.28.1
     # via httpx-aiohttp
     # via llama-stack-client
-httpx-aiohttp==0.1.6
+httpx-aiohttp==0.1.8
     # via llama-stack-client
 idna==3.4
     # via anyio

scripts/utils/upload-artifact.sh

@@ -1,7 +1,9 @@
 #!/usr/bin/env bash
 set -exuo pipefail
 
-RESPONSE=$(curl -X POST "$URL" \
+FILENAME=$(basename dist/*.whl)
+
+RESPONSE=$(curl -X POST "$URL?filename=$FILENAME" \
   -H "Authorization: Bearer $AUTH" \
   -H "Content-Type: application/json")
 
@@ -12,13 +14,13 @@ if [[ "$SIGNED_URL" == "null" ]]; then
   exit 1
 fi
 
-UPLOAD_RESPONSE=$(tar -cz . | curl -v -X PUT \
-  -H "Content-Type: application/gzip" \
-  --data-binary @- "$SIGNED_URL" 2>&1)
+UPLOAD_RESPONSE=$(curl -v -X PUT \
+  -H "Content-Type: binary/octet-stream" \
+  --data-binary "@dist/$FILENAME" "$SIGNED_URL" 2>&1)
 
 if echo "$UPLOAD_RESPONSE" | grep -q "HTTP/[0-9.]* 200"; then
   echo -e "\033[32mUploaded build to Stainless storage.\033[0m"
-  echo -e "\033[32mInstallation: pip install --pre 'https://pkg.stainless.com/s/llama-stack-client-python/$SHA'\033[0m"
+  echo -e "\033[32mInstallation: pip install 'https://pkg.stainless.com/s/llama-stack-client-python/$SHA/$FILENAME'\033[0m"
 else
   echo -e "\033[31mFailed to upload artifact.\033[0m"
   exit 1

src/llama_stack_client/_base_client.py

@@ -529,6 +529,18 @@ def _build_request(
             # work around https://github.com/encode/httpx/discussions/2880
             kwargs["extensions"] = {"sni_hostname": prepared_url.host.replace("_", "-")}
 
+        is_body_allowed = options.method.lower() != "get"
+
+        if is_body_allowed:
+            if isinstance(json_data, bytes):
+                kwargs["content"] = json_data
+            else:
+                kwargs["json"] = json_data if is_given(json_data) else None
+            kwargs["files"] = files
+        else:
+            headers.pop("Content-Type", None)
+            kwargs.pop("data", None)
+
         # TODO: report this error to httpx
         return self._client.build_request(  # pyright: ignore[reportUnknownMemberType]
             headers=headers,
@@ -540,8 +552,6 @@ def _build_request(
             # so that passing a `TypedDict` doesn't cause an error.
             # https://github.com/microsoft/pyright/issues/3526#event-6715453066
             params=self.qs.stringify(cast(Mapping[str, Any], params)) if params else None,
-            json=json_data if is_given(json_data) else None,
-            files=files,
             **kwargs,
         )
 

src/llama_stack_client/_client.py

@@ -41,6 +41,7 @@
     toolgroups,
     vector_dbs,
     completions,
+    moderations,
     scoring_functions,
     synthetic_data_generation,
 )
@@ -91,6 +92,7 @@ class LlamaStackClient(SyncAPIClient):
     post_training: post_training.PostTrainingResource
     providers: providers.ProvidersResource
     routes: routes.RoutesResource
+    moderations: moderations.ModerationsResource
     safety: safety.SafetyResource
     shields: shields.ShieldsResource
     synthetic_data_generation: synthetic_data_generation.SyntheticDataGenerationResource
@@ -177,6 +179,7 @@ def __init__(
         self.post_training = post_training.PostTrainingResource(self)
         self.providers = providers.ProvidersResource(self)
         self.routes = routes.RoutesResource(self)
+        self.moderations = moderations.ModerationsResource(self)
         self.safety = safety.SafetyResource(self)
         self.shields = shields.ShieldsResource(self)
         self.synthetic_data_generation = synthetic_data_generation.SyntheticDataGenerationResource(self)
@@ -315,6 +318,7 @@ class AsyncLlamaStackClient(AsyncAPIClient):
     post_training: post_training.AsyncPostTrainingResource
     providers: providers.AsyncProvidersResource
     routes: routes.AsyncRoutesResource
+    moderations: moderations.AsyncModerationsResource
     safety: safety.AsyncSafetyResource
     shields: shields.AsyncShieldsResource
     synthetic_data_generation: synthetic_data_generation.AsyncSyntheticDataGenerationResource
@@ -401,6 +405,7 @@ def __init__(
         self.post_training = post_training.AsyncPostTrainingResource(self)
         self.providers = providers.AsyncProvidersResource(self)
         self.routes = routes.AsyncRoutesResource(self)
+        self.moderations = moderations.AsyncModerationsResource(self)
         self.safety = safety.AsyncSafetyResource(self)
         self.shields = shields.AsyncShieldsResource(self)
         self.synthetic_data_generation = synthetic_data_generation.AsyncSyntheticDataGenerationResource(self)
@@ -540,6 +545,7 @@ def __init__(self, client: LlamaStackClient) -> None:
         self.post_training = post_training.PostTrainingResourceWithRawResponse(client.post_training)
         self.providers = providers.ProvidersResourceWithRawResponse(client.providers)
         self.routes = routes.RoutesResourceWithRawResponse(client.routes)
+        self.moderations = moderations.ModerationsResourceWithRawResponse(client.moderations)
         self.safety = safety.SafetyResourceWithRawResponse(client.safety)
         self.shields = shields.ShieldsResourceWithRawResponse(client.shields)
         self.synthetic_data_generation = synthetic_data_generation.SyntheticDataGenerationResourceWithRawResponse(
@@ -573,6 +579,7 @@ def __init__(self, client: AsyncLlamaStackClient) -> None:
         self.post_training = post_training.AsyncPostTrainingResourceWithRawResponse(client.post_training)
         self.providers = providers.AsyncProvidersResourceWithRawResponse(client.providers)
         self.routes = routes.AsyncRoutesResourceWithRawResponse(client.routes)
+        self.moderations = moderations.AsyncModerationsResourceWithRawResponse(client.moderations)
         self.safety = safety.AsyncSafetyResourceWithRawResponse(client.safety)
         self.shields = shields.AsyncShieldsResourceWithRawResponse(client.shields)
         self.synthetic_data_generation = synthetic_data_generation.AsyncSyntheticDataGenerationResourceWithRawResponse(
@@ -608,6 +615,7 @@ def __init__(self, client: LlamaStackClient) -> None:
         self.post_training = post_training.PostTrainingResourceWithStreamingResponse(client.post_training)
         self.providers = providers.ProvidersResourceWithStreamingResponse(client.providers)
         self.routes = routes.RoutesResourceWithStreamingResponse(client.routes)
+        self.moderations = moderations.ModerationsResourceWithStreamingResponse(client.moderations)
         self.safety = safety.SafetyResourceWithStreamingResponse(client.safety)
         self.shields = shields.ShieldsResourceWithStreamingResponse(client.shields)
         self.synthetic_data_generation = synthetic_data_generation.SyntheticDataGenerationResourceWithStreamingResponse(
@@ -643,6 +651,7 @@ def __init__(self, client: AsyncLlamaStackClient) -> None:
         self.post_training = post_training.AsyncPostTrainingResourceWithStreamingResponse(client.post_training)
         self.providers = providers.AsyncProvidersResourceWithStreamingResponse(client.providers)
         self.routes = routes.AsyncRoutesResourceWithStreamingResponse(client.routes)
+        self.moderations = moderations.AsyncModerationsResourceWithStreamingResponse(client.moderations)
         self.safety = safety.AsyncSafetyResourceWithStreamingResponse(client.safety)
         self.shields = shields.AsyncShieldsResourceWithStreamingResponse(client.shields)
         self.synthetic_data_generation = (

src/llama_stack_client/_files.py

@@ -69,12 +69,12 @@ def _transform_file(file: FileTypes) -> HttpxFileTypes:
         return file
 
     if is_tuple_t(file):
-        return (file[0], _read_file_content(file[1]), *file[2:])
+        return (file[0], read_file_content(file[1]), *file[2:])
 
     raise TypeError(f"Expected file types input to be a FileContent type or to be a tuple")
 
 
-def _read_file_content(file: FileContent) -> HttpxFileContent:
+def read_file_content(file: FileContent) -> HttpxFileContent:
     if isinstance(file, os.PathLike):
         return pathlib.Path(file).read_bytes()
     return file
@@ -111,12 +111,12 @@ async def _async_transform_file(file: FileTypes) -> HttpxFileTypes:
         return file
 
     if is_tuple_t(file):
-        return (file[0], await _async_read_file_content(file[1]), *file[2:])
+        return (file[0], await async_read_file_content(file[1]), *file[2:])
 
     raise TypeError(f"Expected file types input to be a FileContent type or to be a tuple")
 
 
-async def _async_read_file_content(file: FileContent) -> HttpxFileContent:
+async def async_read_file_content(file: FileContent) -> HttpxFileContent:
     if isinstance(file, os.PathLike):
         return await anyio.Path(file).read_bytes()